richard/etude_lego_jurassic_world
1
Fork 0
Code Issues Activity

Premiers éléments de l'étude

Browse Source
This commit is contained in:
Richard Dern
2025-12-01 21:57:05 +01:00
commit 6494948b3c
50 changed files with 2595 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
tests/test_colors_grid_plot.py Normal file
View File

@@ -0,0 +1,63 @@
"""Tests de la visualisation des couleurs utilisées."""
from pathlib import Path
import matplotlib
from lib.plots.colors_grid import build_hex_positions, load_used_colors, plot_colors_grid
matplotlib.use("Agg")
def write_csv(path: Path, headers: list[str], rows: list[list[str]]) -> None:
"""Écrit un CSV simple pour les besoins de tests."""
path.parent.mkdir(parents=True, exist_ok=True)
with path.open("w", newline="") as csv_file:
import csv
writer = csv.writer(csv_file)
writer.writerow(headers)
writer.writerows(rows)
def test_build_hex_positions() -> None:
"""Construit suffisamment de positions pour toutes les couleurs."""
positions = build_hex_positions(10, columns=4, spacing=1.0)
assert len(positions) == 10
assert positions[0] == (0.0, 0.0)
assert positions[1][0] > positions[0][0]
def test_plot_colors_grid(tmp_path: Path) -> None:
"""Produit un fichier image avec les couleurs utilisées."""
parts_path = tmp_path / "parts_filtered.csv"
colors_path = tmp_path / "colors.csv"
destination_path = tmp_path / "colors_grid.png"
write_csv(
parts_path,
["part_num", "color_rgb", "is_translucent", "set_id", "quantity_in_set", "is_spare"],
[
["3001", "FFFFFF", "false", "1000", "2", "false"],
["3002", "000000", "true", "1000", "5", "false"],
["3003", "FF0000", "false", "1000", "1", "true"],
],
)
write_csv(
colors_path,
["id", "name", "rgb", "is_trans", "num_parts", "num_sets", "y1", "y2"],
[
["1", "White", "FFFFFF", "False", "0", "0", "0", "0"],
["2", "Black", "000000", "True", "0", "0", "0", "0"],
["3", "Red", "FF0000", "False", "0", "0", "0", "0"],
],
)
colors = load_used_colors(parts_path, colors_path)
assert len(colors) == 3
plot_colors_grid(parts_path, colors_path, destination_path)
assert destination_path.exists()
assert destination_path.stat().st_size > 0

91
tests/test_downloader.py Normal file
View File

@@ -0,0 +1,91 @@
"""Tests du module de téléchargement Rebrickable."""
import gzip
from pathlib import Path
import responses
from lib.rebrickable.downloader import (
build_rebrickable_url,
download_rebrickable_file,
download_rebrickable_files,
)
def test_build_rebrickable_url() -> None:
"""Construit l'URL complète vers Rebrickable."""
assert build_rebrickable_url("themes.csv.gz") == (
"https://cdn.rebrickable.com/media/downloads/themes.csv.gz"
)
@responses.activate
def test_download_rebrickable_file(tmp_path: Path) -> None:
"""Télécharge, enregistre et décompresse le fichier compressé."""
file_name = "themes.csv.gz"
uncompressed_content = b"compressed-data"
compressed_body = gzip.compress(uncompressed_content)
responses.add(
responses.GET,
build_rebrickable_url(file_name),
body=compressed_body,
status=200,
)
target_path = download_rebrickable_file(file_name, tmp_path)
assert target_path == tmp_path / "themes.csv"
assert target_path.read_bytes() == uncompressed_content
assert not (tmp_path / file_name).exists()
@responses.activate
def test_download_skips_when_cache_is_fresh(tmp_path: Path) -> None:
"""Ne retélécharge pas un fichier récent et conserve le contenu."""
file_name = "themes.csv.gz"
cached_path = tmp_path / "themes.csv"
cached_path.write_bytes(b"cached")
target_path = download_rebrickable_file(file_name, tmp_path)
assert target_path == cached_path
assert target_path.read_bytes() == b"cached"
assert not (tmp_path / file_name).exists()
assert len(responses.calls) == 0
@responses.activate
def test_download_multiple_rebrickable_files(tmp_path: Path) -> None:
"""Télécharge plusieurs fichiers compressés et les décompresse."""
file_names = [
"inventories.csv.gz",
"inventory_parts.csv.gz",
"parts.csv.gz",
"colors.csv.gz",
]
compressed_bodies = {}
for file_name in file_names:
uncompressed_content = file_name.encode()
compressed_body = gzip.compress(uncompressed_content)
compressed_bodies[file_name] = compressed_body
responses.add(
responses.GET,
build_rebrickable_url(file_name),
body=compressed_body,
status=200,
)
downloaded_paths = download_rebrickable_files(file_names, tmp_path)
assert downloaded_paths == [
tmp_path / "inventories.csv",
tmp_path / "inventory_parts.csv",
tmp_path / "parts.csv",
tmp_path / "colors.csv",
]
assert len(responses.calls) == len(file_names)
for file_name in file_names:
target_path = tmp_path / file_name
decompressed_path = target_path.with_suffix("")
assert decompressed_path.read_bytes() == file_name.encode()
assert not target_path.exists()

77
tests/test_enrich_sets.py Normal file
View File

@@ -0,0 +1,77 @@
"""Tests de l'enrichissement des sets filtrés."""
from pathlib import Path
from lib.rebrickable.enrich_sets import (
build_rebrickable_set_url,
enrich_sets,
extract_set_id,
load_owned_set_ids,
parse_set_collection_root,
write_missing_sets_markdown,
)
def test_extract_set_id_removes_revision() -> None:
"""Supprime la révision de l'identifiant set_num."""
assert extract_set_id("75936-1") == "75936"
def test_build_rebrickable_set_url() -> None:
"""Construit l'URL publique Rebrickable à partir du set_num."""
assert build_rebrickable_set_url("75936-1") == "https://rebrickable.com/sets/75936-1"
def test_parse_set_collection_root_empty_returns_none() -> None:
"""Renvoie None pour une valeur vide."""
assert parse_set_collection_root(" ") is None
def test_load_owned_set_ids_handles_missing_and_collects(tmp_path: Path) -> None:
"""Retourne les sets présents sous forme de dossiers, vide si rien n'existe."""
missing_root = tmp_path / "absent"
assert load_owned_set_ids(missing_root) == set()
root = tmp_path / "collection"
root.mkdir()
(root / "75936").mkdir()
(root / "75944").mkdir()
assert load_owned_set_ids(root) == {"75936", "75944"}
def test_enrich_sets_adds_columns_and_collection(tmp_path: Path) -> None:
"""Enrichit le CSV avec set_id, URL et possession."""
source = tmp_path / "sets_filtered.csv"
destination = tmp_path / "sets_enriched.csv"
source.write_text(
"set_num,name,year,theme_id\n"
"75936-1,T. rex Rampage,2019,602\n"
"10757-1,Raptor Rescue Truck,2018,620\n"
)
enrich_sets(source, destination, {"75936"})
assert destination.read_text() == (
"set_num,name,year,theme_id,set_id,rebrickable_url,in_collection\n"
"75936-1,T. rex Rampage,2019,602,75936,https://rebrickable.com/sets/75936-1,true\n"
"10757-1,Raptor Rescue Truck,2018,620,10757,https://rebrickable.com/sets/10757-1,false\n"
)
def test_write_missing_sets_markdown(tmp_path: Path) -> None:
"""Construit un tableau Markdown des sets non possédés."""
enriched = tmp_path / "sets_enriched.csv"
markdown = tmp_path / "sets_missing.md"
enriched.write_text(
"set_num,name,year,theme_id,set_id,rebrickable_url,in_collection\n"
"75936-1,T. rex Rampage,2019,602,75936,https://rebrickable.com/sets/75936-1,true\n"
"10757-1,Raptor Rescue Truck,2018,620,10757,https://rebrickable.com/sets/10757-1,false\n"
)
write_missing_sets_markdown(enriched, markdown)
assert markdown.read_text() == (
"| set_id | year | name |\n"
"| --- | --- | --- |\n"
"| [10757](https://rebrickable.com/sets/10757-1) | 2018 | Raptor Rescue Truck |\n"
)

37
tests/test_filter_sets.py Normal file
View File

@@ -0,0 +1,37 @@
"""Tests du filtrage des sets par thèmes."""
from pathlib import Path
import pytest
from lib.rebrickable.filter_sets import filter_sets_by_theme, parse_theme_ids
def test_parse_theme_ids_strips_and_validates() -> None:
"""Nettoie la liste et refuse une valeur vide."""
assert parse_theme_ids(" 274 , 602 ,620") == ["274", "602", "620"]
with pytest.raises(ValueError):
parse_theme_ids(" , , ")
def test_filter_sets_by_theme(tmp_path: Path) -> None:
"""Conserve uniquement les sets des thèmes ciblés avec pièces et préserve l'entête."""
source = tmp_path / "sets.csv"
destination = tmp_path / "filtered.csv"
overrides = tmp_path / "overrides.csv"
source.write_text(
"set_num,name,year,theme_id,num_parts,img_url\n"
"75936,T. rex Rampage,2019,602,3120,https://example\n"
"43221,100 Years of Disney Animation Icons,2023,710,0,https://example\n"
"75944,Indominus rex vs. Ankylosaurus,2020,602,1000,https://example\n"
"10757,Raptor Rescue Truck,2018,620,0,https://example\n"
)
overrides.write_text("set_num,num_parts\n75936,3121\n")
filter_sets_by_theme(source, destination, ["602"], overrides)
assert destination.read_text() == (
"set_num,name,year,theme_id,num_parts,img_url\n"
"75936,T. rex Rampage,2019,602,3121,https://example\n"
"75944,Indominus rex vs. Ankylosaurus,2020,602,1000,https://example\n"
)

144
tests/test_inventory_gaps.py Normal file
View File

@@ -0,0 +1,144 @@
"""Tests des écarts d'inventaire calculés depuis parts_filtered.csv."""
import csv
from pathlib import Path
from lib.rebrickable.inventory_reconciliation import (
compute_inventory_gaps,
index_sets_by_num,
write_inventory_gaps_csv,
write_inventory_gaps_markdown,
)
def write_csv(path: Path, headers: list[str], rows: list[list[str]]) -> None:
"""Écrit un CSV simple pour les besoins des tests."""
with path.open("w", newline="") as csv_file:
writer = csv.writer(csv_file)
writer.writerow(headers)
writer.writerows(rows)
def test_compute_inventory_gaps_excludes_spares(tmp_path: Path) -> None:
"""Ignore les pièces de rechange et ne conserve que les sets en écart."""
sets_path = tmp_path / "sets_enriched.csv"
parts_path = tmp_path / "parts_filtered.csv"
write_csv(
sets_path,
["set_num", "set_id", "num_parts", "in_collection"],
[
["1000-1", "1000", "4", "true"],
["2000-1", "2000", "3", "false"],
["3000-1", "3000", "1", "true"],
],
)
write_csv(
parts_path,
["part_num", "color_rgb", "is_translucent", "set_num", "set_id", "quantity_in_set", "is_spare"],
[
["A", "AAAAAA", "false", "1000-1", "1000", "2", "false"],
["B", "BBBBBB", "false", "1000-1", "1000", "2", "false"],
["S", "SSSSSS", "false", "1000-1", "1000", "5", "true"],
["C", "CCCCCC", "false", "2000-1", "2000", "2", "false"],
["D", "DDDDDD", "false", "3000-1", "3000", "1", "false"],
],
)
gaps = compute_inventory_gaps(sets_path, parts_path)
assert gaps == [
{
"set_num": "1000-1",
"set_id": "1000",
"expected_parts": 4,
"inventory_parts": 9,
"inventory_parts_non_spare": 4,
"delta": 5,
"delta_non_spare": 0,
"in_collection": "true",
},
{
"set_num": "2000-1",
"set_id": "2000",
"expected_parts": 3,
"inventory_parts": 2,
"inventory_parts_non_spare": 2,
"delta": 1,
"delta_non_spare": 1,
"in_collection": "false",
}
]
def test_write_inventory_gaps_csv(tmp_path: Path) -> None:
"""Sérialise le rapport d'écarts dans un CSV dédié."""
destination_path = tmp_path / "inventory_gaps.csv"
rows = [
{
"set_num": "2000-1",
"set_id": "2000",
"expected_parts": 3,
"inventory_parts": 2,
"inventory_parts_non_spare": 2,
"delta": 1,
"delta_non_spare": 1,
"in_collection": "false",
}
]
write_inventory_gaps_csv(destination_path, rows)
with destination_path.open() as csv_file:
written_rows = list(csv.DictReader(csv_file))
assert written_rows == [
{
"set_num": "2000-1",
"set_id": "2000",
"expected_parts": "3",
"inventory_parts": "2",
"inventory_parts_non_spare": "2",
"delta": "1",
"delta_non_spare": "1",
"in_collection": "false",
}
]
def test_write_inventory_gaps_markdown(tmp_path: Path) -> None:
"""Produit un tableau Markdown listant les sets en écart."""
destination_path = tmp_path / "inventory_gaps.md"
gaps = [
{
"set_num": "2000-1",
"set_id": "2000",
"expected_parts": 3,
"inventory_parts": 2,
"inventory_parts_non_spare": 2,
"delta": 1,
"delta_non_spare": 1,
"in_collection": "false",
}
]
sets = [
{
"set_num": "2000-1",
"set_id": "2000",
"num_parts": "3",
"name": "Test Set",
"year": "2020",
"rebrickable_url": "https://rebrickable.com/sets/2000-1",
"in_collection": "false",
}
]
write_inventory_gaps_markdown(destination_path, gaps, index_sets_by_num(sets))
with destination_path.open() as markdown_file:
content = markdown_file.read().splitlines()
assert content[0].startswith("| set_id | name |")
assert (
"| [2000](https://rebrickable.com/sets/2000-1) | Test Set | 2020 | 1 | 1 | 3 | 2 | 2 | false | [PDF](https://www.lego.com/service/buildinginstructions/2000) |"
in content
)

22
tests/test_milestones.py Normal file
View File

@@ -0,0 +1,22 @@
"""Tests du chargement des jalons configurables."""
from pathlib import Path
from lib.milestones import load_milestones
def test_load_milestones_reads_csv(tmp_path: Path) -> None:
"""Charge le CSV et convertit l'année en entier."""
source = tmp_path / "milestones.csv"
source.write_text(
"year,description\n"
"1993,Sortie du film Jurassic Park\n"
"1997,Sortie du film The Lost World: Jurassic Park\n"
)
milestones = load_milestones(source)
assert milestones == [
{"year": 1993, "description": "Sortie du film Jurassic Park"},
{"year": 1997, "description": "Sortie du film The Lost World: Jurassic Park"},
]

140
tests/test_parts_inventory.py Normal file
View File

@@ -0,0 +1,140 @@
"""Tests de construction du fichier parts_filtered.csv."""
import csv
from pathlib import Path
from lib.rebrickable.parts_inventory import write_parts_filtered
def write_csv(path: Path, headers: list[str], rows: list[list[str]]) -> None:
"""Écrit un CSV simple pour les besoins de tests."""
with path.open("w", newline="") as csv_file:
writer = csv.writer(csv_file)
writer.writerow(headers)
writer.writerows(rows)
def test_write_parts_filtered(tmp_path: Path) -> None:
"""Assemble les pièces par set avec la dernière version d'inventaire."""
sets_path = tmp_path / "sets_enriched.csv"
inventories_path = tmp_path / "inventories.csv"
inventory_parts_path = tmp_path / "inventory_parts.csv"
colors_path = tmp_path / "colors.csv"
inventory_minifigs_path = tmp_path / "inventory_minifigs.csv"
minifigs_path = tmp_path / "minifigs.csv"
destination_path = tmp_path / "parts_filtered.csv"
write_csv(
sets_path,
["set_num", "set_id", "name", "num_parts"],
[
["1234-1", "1234", "Sample Set A", "9"],
["5678-1", "5678", "Sample Set B", "2"],
],
)
write_csv(
inventories_path,
["id", "version", "set_num"],
[
["1", "1", "1234-1"],
["2", "2", "1234-1"],
["3", "1", "5678-1"],
["4", "1", "fig-123"],
],
)
write_csv(
inventory_parts_path,
["inventory_id", "part_num", "color_id", "quantity", "is_spare", "img_url"],
[
["2", "3001", "1", "4", "False", ""],
["2", "3002", "2", "1", "True", ""],
["3", "3003", "3", "2", "False", ""],
["4", "mf-1", "2", "1", "False", ""],
["4", "mf-2", "3", "2", "False", ""],
],
)
write_csv(
inventory_minifigs_path,
["inventory_id", "fig_num", "quantity"],
[
["2", "fig-123", "1"],
],
)
write_csv(
minifigs_path,
["fig_num", "name", "num_parts", "img_url"],
[
["fig-123", "Sample Minifig", "2", ""],
],
)
write_csv(
colors_path,
["id", "name", "rgb", "is_trans", "num_parts", "num_sets", "y1", "y2"],
[
["1", "White", "FFFFFF", "False", "0", "0", "0", "0"],
["2", "Black", "000000", "True", "0", "0", "0", "0"],
["3", "Red", "FF0000", "False", "0", "0", "0", "0"],
],
)
write_parts_filtered(
sets_path,
inventories_path,
inventory_parts_path,
colors_path,
inventory_minifigs_path,
minifigs_path,
destination_path,
)
with destination_path.open() as result_file:
reader = csv.DictReader(result_file)
rows = list(reader)
assert rows == [
{
"part_num": "3001",
"color_rgb": "FFFFFF",
"is_translucent": "false",
"set_num": "1234-1",
"set_id": "1234",
"quantity_in_set": "4",
"is_spare": "false",
},
{
"part_num": "3002",
"color_rgb": "000000",
"is_translucent": "true",
"set_num": "1234-1",
"set_id": "1234",
"quantity_in_set": "1",
"is_spare": "true",
},
{
"part_num": "mf-1",
"color_rgb": "000000",
"is_translucent": "true",
"set_num": "1234-1",
"set_id": "1234",
"quantity_in_set": "1",
"is_spare": "false",
},
{
"part_num": "mf-2",
"color_rgb": "FF0000",
"is_translucent": "false",
"set_num": "1234-1",
"set_id": "1234",
"quantity_in_set": "2",
"is_spare": "false",
},
{
"part_num": "3003",
"color_rgb": "FF0000",
"is_translucent": "false",
"set_num": "5678-1",
"set_id": "5678",
"quantity_in_set": "2",
"is_spare": "false",
},
]

54
tests/test_parts_per_set_plot.py Normal file
View File

@@ -0,0 +1,54 @@
"""Tests des graphiques sur la moyenne de pièces par set."""
from pathlib import Path
import matplotlib
from lib.plots.parts_per_set import (
compute_average_parts_per_set,
compute_rolling_mean,
plot_parts_per_set,
)
matplotlib.use("Agg")
def test_compute_average_parts_per_set() -> None:
"""Calcule la moyenne annuelle pièces/set."""
rows = [
{"year": "2020", "num_parts": "100"},
{"year": "2020", "num_parts": "200"},
{"year": "2021", "num_parts": "150"},
]
series = compute_average_parts_per_set(rows)
assert series == [(2020, 150.0), (2021, 150.0)]
def test_compute_rolling_mean() -> None:
"""Calcule une moyenne glissante 2 ans."""
series = [(2020, 100.0), (2021, 200.0), (2022, 300.0)]
rolling = compute_rolling_mean(series, 2)
assert rolling == [(2020, 0.0), (2021, 150.0), (2022, 250.0)]
def test_plot_parts_per_set_creates_figure(tmp_path: Path) -> None:
"""Génère le fichier image avec moyennes annuelle et glissante."""
enriched = tmp_path / "sets_enriched.csv"
milestones = tmp_path / "milestones.csv"
destination = tmp_path / "figures" / "step07" / "avg_parts_per_set.png"
enriched.write_text(
"set_num,name,year,theme_id,num_parts,img_url,set_id,rebrickable_url,in_collection\n"
"75936-1,T. rex Rampage,2019,602,3120,https://example,75936,https://example,true\n"
"75944-1,Indominus rex vs. Ankylosaurus,2020,602,1000,https://example,75944,https://example,false\n"
)
milestones.write_text("year,description\n2019,LEGO Jurassic World: Legend of Isla Nublar\n")
plot_parts_per_set(enriched, milestones, destination)
assert destination.exists()
assert destination.stat().st_size > 0

85
tests/test_parts_stats.py Normal file
View File

@@ -0,0 +1,85 @@
"""Tests des statistiques simples sur les pièces filtrées."""
import csv
from pathlib import Path
from lib.rebrickable.parts_stats import build_stats, read_rows, write_parts_stats
def write_csv(path: Path, headers: list[str], rows: list[list[str]]) -> None:
"""Écrit un CSV simple pour les besoins de tests."""
with path.open("w", newline="") as csv_file:
writer = csv.writer(csv_file)
writer.writerow(headers)
writer.writerows(rows)
def test_build_stats(tmp_path: Path) -> None:
"""Calcule les statistiques principales sans les pièces de rechange."""
parts_path = tmp_path / "parts_filtered.csv"
sets_path = tmp_path / "sets_enriched.csv"
stats_path = tmp_path / "stats.csv"
write_csv(
parts_path,
["part_num", "color_rgb", "is_translucent", "set_num", "set_id", "quantity_in_set", "is_spare"],
[
["3001", "FFFFFF", "false", "1000-1", "1000", "2", "false"],
["3001", "FFFFFF", "false", "2000-1", "2000", "1", "false"],
["3002", "000000", "true", "1000-1", "1000", "5", "false"],
["3003", "FF0000", "false", "1000-1", "1000", "1", "true"],
],
)
write_csv(
sets_path,
["set_num", "set_id", "num_parts", "in_collection"],
[
["1000-1", "1000", "8", "true"],
["2000-1", "2000", "1", "false"],
],
)
write_csv(
stats_path,
["libelle", "valeur"],
[
["Total de pièces pour les thèmes filtrés", "9"],
],
)
stats = build_stats(read_rows(parts_path), sets_path, parts_path, stats_path)
assert stats == [
("Total de variations de pièces (hors rechanges)", "2"),
(
"Pièce la moins utilisée (référence + couleur)",
"3001 / FFFFFF / false (3)",
),
(
"Pièce la plus commune (référence + couleur)",
"3002 / 000000 / true (5)",
),
("Total de couleurs utilisées (hors rechanges)", "2"),
("Total de pièces hors rechanges", "8"),
("Ecart total catalogue (stats) - inventaire (hors rechanges)", "1"),
("Nombre de sets en écart inventaire/catalogue", "0"),
("Ecart maximal inventaire/catalogue", "none (0)"),
]
def test_write_parts_stats(tmp_path: Path) -> None:
"""Écrit un CSV de statistiques."""
destination_path = tmp_path / "parts_stats.csv"
stats = [
("A", "1"),
("B", "2"),
]
write_parts_stats(destination_path, stats)
with destination_path.open() as csv_file:
rows = list(csv.reader(csv_file))
assert rows == [
["libelle", "valeur"],
["A", "1"],
["B", "2"],
]

60
tests/test_sets_per_year_plot.py Normal file
View File

@@ -0,0 +1,60 @@
"""Tests du graphique des sets par année."""
import matplotlib
from pathlib import Path
from lib.plots.sets_per_year import (
compute_parts_per_year,
compute_sets_per_year,
plot_sets_per_year,
)
matplotlib.use("Agg")
def test_compute_sets_per_year_counts_and_sorts() -> None:
"""Compte les sets par année et renvoie une liste triée."""
rows = [
{"year": "2020"},
{"year": "2019"},
{"year": "2020"},
]
series = compute_sets_per_year(rows)
assert series == [(2019, 1), (2020, 2)]
def test_compute_parts_per_year_sums_and_sorts() -> None:
"""Somme les pièces par année et renvoie une liste triée."""
rows = [
{"year": "2020", "num_parts": "10"},
{"year": "2019", "num_parts": "5"},
{"year": "2020", "num_parts": "1"},
]
series = compute_parts_per_year(rows)
assert series == [(2019, 5), (2020, 11)]
def test_plot_sets_per_year_creates_figure(tmp_path: Path) -> None:
"""Génère un fichier image avec les jalons fournis."""
enriched = tmp_path / "sets_enriched.csv"
milestones = tmp_path / "milestones.csv"
destination = tmp_path / "figures" / "step07" / "sets_per_year.png"
enriched.write_text(
"set_num,name,year,theme_id,num_parts,img_url,set_id,rebrickable_url,in_collection\n"
"75936-1,T. rex Rampage,2019,602,3120,https://example,75936,https://example,true\n"
"75944-1,Indominus rex vs. Ankylosaurus,2020,602,1000,https://example,75944,https://example,false\n"
)
milestones.write_text(
"year,description\n"
"2019,Diffusion LEGO Jurassic World: Legend of Isla Nublar\n"
)
plot_sets_per_year(enriched, milestones, destination)
assert destination.exists()
assert destination.stat().st_size > 0

83
tests/test_stats.py Normal file
View File

@@ -0,0 +1,83 @@
"""Tests des statistiques calculées sur les sets LEGO filtrés."""
from lib.rebrickable.stats import compute_basic_stats, write_stats_csv
def test_compute_basic_stats_returns_expected_values(tmp_path) -> None:
"""Calcule les statistiques principales sur un échantillon maîtrisé."""
themes = [
{"id": "602", "name": "Jurassic World", "parent_id": ""},
{"id": "274", "name": "Jurassic Park III", "parent_id": "273"},
]
all_sets = [
{"set_num": "123-1", "name": "A", "year": "2020", "theme_id": "602", "num_parts": "100", "img_url": ""},
{"set_num": "124-1", "name": "B", "year": "2021", "theme_id": "602", "num_parts": "200", "img_url": ""},
{"set_num": "125-1", "name": "C", "year": "2021", "theme_id": "274", "num_parts": "300", "img_url": ""},
]
filtered_sets = [
{"set_num": "123-1", "name": "A", "year": "2020", "theme_id": "602", "num_parts": "100", "img_url": ""},
{"set_num": "124-1", "name": "B", "year": "2021", "theme_id": "602", "num_parts": "200", "img_url": ""},
]
enriched_sets = [
{
"set_num": "123-1",
"name": "A",
"year": "2020",
"theme_id": "602",
"num_parts": "100",
"img_url": "",
"set_id": "123",
"rebrickable_url": "",
"in_collection": "true",
},
{
"set_num": "124-1",
"name": "B",
"year": "2021",
"theme_id": "602",
"num_parts": "200",
"img_url": "",
"set_id": "124",
"rebrickable_url": "",
"in_collection": "false",
},
]
stats = compute_basic_stats(themes, all_sets, filtered_sets, enriched_sets)
assert stats == [
("Nombre total de sets (catalogue complet)", "3"),
("Nombre total de thèmes (catalogue complet)", "2"),
("Nombre de sets après filtrage (thèmes ciblés)", "2"),
("Nombre moyen de sets par thème (catalogue complet)", "1.50"),
("Pourcentage des sets filtrés vs total", "66.67%"),
("Taux de possession (thèmes filtrés)", "50.00%"),
("Sets dans la collection", "1"),
("Sets manquants pour la collection", "1"),
("Nombre moyen de pièces par set (thèmes filtrés)", "150.00"),
("Médiane de pièces par set (thèmes filtrés)", "150.00"),
("Nombre moyen de sets commercialisés par an (thèmes filtrés)", "1.00"),
("Total de pièces pour les thèmes filtrés", "300"),
("Total de pièces des sets possédés", "100"),
("Pourcentage de pièces possédées (thèmes filtrés)", "33.33%"),
("Nombre de thèmes filtrés", "1"),
("Première année de sortie (thèmes filtrés)", "2020"),
("Dernière année de sortie (thèmes filtrés)", "2021"),
("Année la plus prolifique (thèmes filtrés)", "2020 (1 sets)"),
("Set avec le plus de pièces (thèmes filtrés)", "124-1 - B (200 pièces)"),
("Set avec le moins de pièces (thèmes filtrés)", "123-1 - A (100 pièces)"),
("Set le plus ancien (thèmes filtrés)", "123-1 - A (2020)"),
("Set le plus récent (thèmes filtrés)", "124-1 - B (2021)"),
("Nombre moyen de pièces des sets possédés", "100.00"),
("Nombre moyen de pièces des sets manquants", "200.00"),
]
def test_write_stats_csv_outputs_two_columns(tmp_path) -> None:
"""Écrit un CSV simple avec libellé et valeur."""
destination = tmp_path / "stats.csv"
stats = [("A", "1"), ("B", "2")]
write_stats_csv(destination, stats)
assert destination.read_text() == "libelle,valeur\nA,1\nB,2\n"